Stacking Complementary CLAP Embeddings for Improving Text-Audio Alignment Correspondence Scoring
Sheng Li, Jiyi Li, Takahiro Shinozaki
· 0 citations
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Preprint
Aug 2026
Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech
Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis pipelines typically generate dialogue content first and then insert interruptions, overlap, and backchannels using handcrafted markers or timing rules, makin...
Pengcheng Wang, Sheng Li, Ji-Yi Li et al.
· 0 citations